Related papers: The Conversations Beneath the Code: Triadic Data f…
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have…
Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub…
LLM-based agentic coding assistants lack persistent memory: they lose coherence across sessions, forget project conventions, and repeat known mistakes. Recent studies characterize how developers configure agents through manifest files, but…
Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…
Much of software engineering research focuses on tools, algorithms, and optimization of software. Recently, we, as a community, have come to acknowledge that there is a gap in meta-research and addressing the human-factors in software…
AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat, the first large-scale dataset of real coding agent sessions…
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…
LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…
Advancements in foundation models have catalyzed research in Embodied AI to develop interactive agents capable of environmental reasoning and interaction. Developing such agents requires diverse, large-scale datasets. Prior frameworks…
Software development is a sociotechnical and human-centered endeavor in which human factors directly influence quality, productivity, and innovation capacity. In this context, career development in computing goes beyond technical mastery,…
Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process…
Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…
Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying…
Conveying human goals to autonomous systems (AS) occurs both when the system is being designed and when it is being operated. The design-step conveyance is typically mediated by robotics and AI engineers, who must appropriately capture…
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while…
Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting…
Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However,…
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…